OpenCode & ChatGPT passthrough

Route OpenCode's OpenAI provider through llama-dash to log and inspect ChatGPT subscription requests. OpenCode keeps ownership of the subscription OAuth bearer; llama-dash preserves it while forwarding requests to the ChatGPT Codex backend.

Client config

Connect OpenCode to OpenAI with its ChatGPT subscription first. Then set the OpenAI provider base URL in ~/.config/opencode/opencode.jsonc:

{
  "provider": {
    "openai": {
      "options": {
        "baseURL": "https://<llama-dash-host>/v1"
      },
    }
  }
}

Restart OpenCode after changing its config:

opencode2 service restart

Do not set an OpenAI API key for this flow. OpenCode supplies its subscription credentials, and llama-dash forwards them unchanged.

Routing rule

In Policies, add a first-match routing rule for the OpenAI Responses API:

• Match endpoint /v1/responses.
• Match the exact OpenCode model IDs you use, such as gpt-5.6-terra, gpt-5.6-luna, and gpt-5.6-sol.
• Set action to continue.
• Set auth mode to passthrough and preserve the client Authorization header.
• Set direct target to https://chatgpt.com/backend-api/codex.

Do not leave Requested model empty. Other OpenAI-compatible clients can use /v1/responses; exact model matching limits this rule to the selected OpenCode models.

The resulting requests remain visible in Requests, including routing metadata, the redacted authorization header, and OpenCode attribution.